Computer aided quantification of intratumoral stroma yields an independent prognosticator in rectal cancer

An existing cohort of 154 patients [8] with rectal adenocarcinoma stages I-III was used. All patients received curative surgery in the period 1996–2006 at the Medisch Spectrum Twente hospital (The Netherlands). No patient was neoadjuvantly treated with radiotherapy and/or chemotherapy or died within 30 days after surgery. At the time of surgery, none of the patients had known distant metastases, inflammatory bowel disease, hereditary nonpolyposis colorectal cancer (HNPCC) or other/earlier cancers. Histopathological data were obtained from the Laboratory for Pathology Eastern Netherlands (LabPON). Clinical data were obtained from the Medisch Spectrum Twente hospital and the Netherlands Comprehensive Cancer Organization (IKNL). Collected clinicopathological data included tumor grade (differentiation), depth of invasion (pT) and lymph node involvement (pN) according to the Union Internationale Contre le Cancer/American Joint Cancer Committee (UICC/AJCC) TNM staging system [1]. Data regarding adjuvant therapy and local or distant recurrence were also available.

According to standard procedures at LabPON, formalin fixed and paraffin embedded tissue sections were cut at 2 μm and stained in an automatic stainer with hematoxylin and eosin (H&E) for routine diagnostic purposes. For the present study, a single slide per patient was selected which contained the most invasive part of the tumor and was used in diagnostics to assess the tumor pT-status. Slides were scanned at ×200 total magnification (tissue level pixel size ~0.455 μm/pixel) using a Hamamatsu NanoZoomer 2.0-HT (C9600–13) scanner (Herrsching, Germany).

Two observers (GvP, WM; both > 10 years of experience with TSR scoring) independently scored the slides using a conventional light microscope according to a previously published protocol for TSR assessment [9, 10]. Briefly, the procedure consisted of 1) coarse localization of the tissue area with the highest intratumoral stroma content at low microscope magnification, and 2) selection of one field of view at ×100 total magnification and visual estimation of the tumor-stroma ratio (TSR-visual) in the selected circular region. Ideally, the selected region should meet the following criteria: high intratumoral stroma content (predominantly found at the invasive margin of a tumor); presence of tumor cells at all borders of the field of view; no large quantities of muscle, mucus, necrosis or large vessels; and no tears or tissue retraction artefacts. As much as possible, the region with the highest stroma content (stroma hot-spot) was selected that met all the above requirements. TSR-visual was estimated by both observers independently, using 10% increments. As a result of the specific microscope and lenses used, the specimen-level diameter of the circular region was 1.8 mm at ×100 magnification. There is a lot of variation among published studies concerning used TSR procedures (e.g. major differences in the location and size of the assessed tissue regions as well as what was actually measured: relative tumor or stroma content). For clarity, in this study the tumor-stroma ratio was defined as TSR = 100% × [intratumoral stroma area] / [tumor area + intratumoral stroma area]. Lumen, tears and other tissue types in the selected circular region were excluded during visual estimation. Lastly, the tissue region considered most suitable for TSR assessment was identified during a consensus meeting between the two observers in which 1) a binary TSR consensus score was determined: ‘stroma-low’ or ‘stroma-high’, and 2), the center of the stroma hot-spot was marked on the glass slide.

To study the value of applying a deep learning algorithm for automated TSR assessment (TSR-auto), a CNN was developed similar to a previously published algorithm [20]. The CNN performs tissue segmentation (i.e. subdivision of tissue areas) of H&E-stained rectal cancer WSI into nine different classes: tumor, intratumoral stroma, necrosis, muscle, healthy epithelium, fatty tissue, lymphocytes, mucus and erythrocytes. The CNN was trained using manually annotated regions in 74 WSI taken from the cohort used in this study. Regions to annotate were selected for covering tissue variety across WSI, rather than producing exhaustive annotations on a small number of WSI. Annotations were produced by a pathology researcher (OG) and a medical student, and were checked and corrected when deemed necessary by an experienced pathologist (AB). A digital staining normalization method [21] was applied to all WSI as a pre-processing step to accommodate for typical differences in tissue staining intensities, caused by variations in slide preparation. Unlike Ciompi et al. [20], here we used patches of 256 × 256 pixels for classification, which experimentally showed to improve performance and produce a smoother segmentation map (data not shown). Performance of the system was assessed by segmenting all WSI in the dataset in a five-fold cross validation fashion (at WSI level) and evaluating accuracy in all annotated regions.

To enable comparison, the CNN-based TSR-auto was computed in the same circular region (with 1.8 mm diameter) that was selected by the observers at the consensus meeting, where TSR-visual was assessed. The corresponding image data were extracted from each WSI as circles with a diameter of ~4000 pixels and processed further by the CNN described above (Fig. 1). Segmentation of a WSI into nine different tissue classes enabled in- and exclusion of specific tissue types comparable to the visual assessment procedure. The used definition of TSR-auto is similar to TSR-visual, expressing the area consisting of stroma as a percentage of the area occupied by both tumor and stroma.

In this study, TSR-visual and TSR-auto were compared as prognostic factors in rectal cancer. Statistical analyses were performed using IBM SPSS software v24.0 (Armonk, NY, USA). The intraclass correlation coefficient (ICC) was used to determine the correlation between TSR assessed by two observers and by the automated method. To investigate a possible relationship between clinicopathological variables and the numerical values of TSR-visual and TSR-auto, Mann–Whitney U and Kruskal–Wallis tests were performed for two- and multi-class variables, respectively. For further statistical analysis, TSR-visual and TSR-auto were dichotomized, subdividing patients into two groups: ‘stroma-low’ and ‘stroma-high’. Dichotomization of TSR-visual was performed based on a cut-off value previously established [10] on 63 colon cancer cases: stroma-high = TSR-visual > 50% and stroma-low = TSR-visual ≤ 50%. In this study, we analyzed results for two different cut-off values for TSR-auto since the optimal cut-off value for the automated approach is not yet established. One method of dichotomization used the ‘50% stroma cut-off’, similar to TSR-visual, referred to as TSR-auto(50%), and the other dichotomization method was based on the median value for all measured TSR-auto values, referred to as TSR-auto(median), yielding equal numbers of patients in stroma-low and stroma-high groups.

Of 154 cases projected for inclusion in this study, twelve cases with mucinous carcinoma were excluded as these tumors exhibit largely different TSR values. Twelve other cases were excluded because, at the time of writing, the required slides or data were unavailable. One case was excluded because the corresponding tissue slide did not contain invasive carcinoma.

The median follow-up time for the remaining 129 patients used in the present study was 5.6 years (interquartile range 2.3–8.3). The median age of the patients at the time of surgery was 67 years (interquartile range 59–74). Further clinicopathological data can be found in Table 1. There was no significant correlation between the clinicopathological variables and assessed values of TSR-visual or TSR-auto (p > 0.05).

Measures of sensitivity and specificity per tissue type as well as overall accuracy were assessed for the automatic method by pixel-wise comparison of predicted labels with ground truth labels in manually annotated regions. We found that the overall accuracy was 94.6%, which shows improvement on what was reported by Ciompi et al. [20]. Values of per-class sensitivity and specificity are reported in Table 2.

Examples of tissue segmentation by the CNN in four circular regions selected by the observers are shown in Fig. 1. In line with the high classification accuracy, good segmentation of tumor, stroma and other tissues types was observed. Further qualitative inspection of the circular regions revealed some minor segmentation errors. Directly at the stroma-tumor interface, a very thin band of stroma pixels is often misclassified as tumor. Likewise, however, small groups of tumor cells (e.g. tumor buds, or thin tumor structures) were sometimes misclassified as stroma.

The ICC between the two observers for the assessment of TSR was 0.736 (95% confidence interval (95% CI) 0.646–0.806). The co-occurrence of TSR scores assessed by the two observers is depicted in Fig. 2. The ICC’s between TSR-auto and TSR-visual were 0.475 (95% CI 0.330–0.598) and 0.411 (95% CI 0.257–0.545) for observers 1 and 2, respectively.

A moderate agreement between the two observers (κ = 0.578) was found after dichotomizing TSR-visual on basis of the 50% cut-off as described in section 2.5. Using the identical cut-off for TSR-auto, we observed only a fair agreement between TSR-visual and TSR-auto (κ = 0.239). Agreement improved considerably (κ = 0.521) when the median was used as cut-off for TSR-auto, resulting in: stroma-low = TSR-auto ≤ 65.47% and stroma-high = TSR-auto > 65.47%. Patients assigned to stroma-low or stroma-high groups by the observers and the automatic method are detailed in Tables 3, 4 and 5.

Survival analysis generally showed a worse outcome for stroma-high patients compared to stroma-low patients (Fig. 3), independent of the method of TSR assessment used (visual versus automated). For TSR-visual, the 5-year survival rates for stroma-low versus stroma-high cases were 71.0% versus 58.8% for DSS and 65.6% versus 49.1% for DFS. For TSR-auto(50%), the 5-year survival rates for stroma-low versus stroma-high cases were 86.6% versus 60.7% for DSS and 76.8% versus 54.9% for DFS. For TSR-auto(median), the 5-year survival rates for stroma-low versus stroma-high cases, were 76.1% versus 58.4% for DSS and 70.0% versus 50.7% for DFS.

For TSR-visual, a significantly lower DSS was seen in the stroma-high group compared to the stroma-low group (p = 0.042), but not for DFS (p = 0.182). Similarly, for TSR-auto(50%) this difference was significant for DSS (p = 0.018), but not for DFS (p = 0.066). For TSR-auto(median), both DSS and DFS were found to be significantly lower in the stroma-high group compared to the stroma-low group (p = 0.007 and p = 0.021, respectively). After stratification for TNM stage, stroma-high was also found to be associated with worse survival in stage II rectal cancer patients (n = 45), but this result was only significant for TSR-auto(median) (DSS p = 0.003 and DFS p = 0.015).

Hazard ratios (HR) and 95% CIs were determined for both DSS and DFS (Tables 6 and 7). In univariate analysis, all methods for TSR assessment were found to be prognostic for DSS: TSR-visual HR = 1.83 (95% CI 1.01–3.30); TSR-auto(50%) HR = 2.71 (95% CI 1.14–6.40); and TSR-auto(median) HR = 2.31 (95% CI 1.24–4.30). For DFS, only TSR-auto(median) was found to be prognostic with HR = 1.96 (95% CI 1.10–3.51). After stratification for TNM stage, only TSR-auto(median) was found to be prognostic for stage II rectal cancer patients, both for DSS (univariate HR = 4.13 (95% CI 1.53–11.16)) and DFS (univariate HR = 3.05 (95% CI 1.19–7.81)).

In multivariate analysis, automated TSR assessment was found to be prognostic independent of age, gender, pT-stage, lymph node status, tumor grade, and whether adjuvant therapy was given, both for DSS: TSR-auto(50%) HR = 3.11 (95% CI 1.26–7.70) and TSR-auto(median) HR = 2.48 (95% CI 1.29–4.78), and for DFS: TSR-auto(50%) (HR = 2.39 (95% CI 1.07–5.38)) and TSR-auto(median) (HR = 2.05 (95% CI 1.11–3.78)). TSR-visual was not found to serve as an independent prognostic factor.